© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2917
    Prev
    Next
    INDEX
    Explanations

    URLs and item codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yth
    1.79
    ქ
    1.78
    Фе
    1.77
    ဳ
    1.76
    Ша
    1.75
    Ж
    1.72
    躇
    1.71
     Фе
    1.68
    Лу
    1.68
    撅
    1.67
    POSITIVE LOGITS
     preorder
    1.72
    seller
    1.70
     retailer
    1.70
     seller
    1.65
     shopper
    1.57
     buyer
    1.54
     merchandise
    1.52
     refund
    1.51
     reseller
    1.50
     searchable
    1.48
    Activations Density 0.003%

    No Known Activations